Intelligent fault alarm system in unmanned aerial vehicle environment perception

Abstract

The invention discloses an intelligent fault alarm system in unmanned aerial vehicle environment perception, and relates to the technical field of unmanned aerial vehicles, the system comprises the following components: an environment perception module, an environment parameter analysis and decision unit, a fault early warning and alarm module and an adaptive adjustment module; key parameters in an extreme environment are monitored in real time by integrating multiple sensors, rapid analysis and decision making are carried out in combination with an intelligent algorithm, potential risks possibly faced by the unmanned aerial vehicle can be found and early warned in time, and an enhanced heat dissipation mode and a high-temperature alarm are automatically started in a high-temperature environment, so that electronic components are effectively prevented from being overheated and damaged; in a low-temperature environment, heat preservation measures and low-temperature alarm are taken for key components, so that stable performance of key components such as a battery is guaranteed, and flight accidents caused by failure of the battery are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to an intelligent fault alarm system in unmanned aerial vehicle environment perception. Background Art

[0002] As one of the rapidly developing high-tech technologies in recent years, UAV technology has demonstrated its unique advantages and broad application prospects in many fields. From environmental monitoring to disaster relief, from agricultural plant protection to geographical exploration, UAVs have become an indispensable part of modern science and technology with their flexibility, low cost and wide field of view. With the continuous advancement of technology, UAVs are increasingly used to perform complex tasks in extreme environmental conditions, which puts higher requirements on the environmental adaptability and stability of UAVs.

[0003] Although existing drone technology has made remarkable achievements in many aspects, its application in extreme environmental conditions still faces many challenges. When encountering extreme environments such as high temperature, low temperature or high altitude, traditional drones often experience problems such as overheating of electronic components, sharp decline in battery performance, and increased wear of mechanical parts. These problems directly affect the stability and safety of the drone. In high temperature environments, the electronic components inside the drone are easily damaged by overheating, affecting flight control. In low temperature environments, battery performance decreases significantly, flight time is shortened, and mechanical parts may freeze or lose flexibility due to low temperatures. In high-altitude environments, the thin air reduces engine efficiency and limits flight performance. In addition, most traditional drones lack intelligent fault warning systems and are unable to monitor environmental changes in real time and warn of potential faults in advance, increasing flight risks.

[0004] In view of the above problems, it is necessary to optimize the existing intelligent fault alarm system in the environmental perception of UAVs. By integrating multiple sensors, intelligent algorithms and adaptive adjustment mechanisms, real-time monitoring and evaluation of the current environmental parameters of the UAV can be realized, and the working state of the UAV can be automatically adjusted accordingly. At the same time, an alarm will be issued immediately when a potential fault is detected. Therefore, it is of great significance to develop an intelligent fault alarm system in the environmental perception of UAVs that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and provide an intelligent fault alarm system in UAV environmental perception. It can integrate multiple sensors, intelligent algorithms and adaptive adjustment mechanisms. The system can realize comprehensive and real-time monitoring of the environment in which the UAV is located, and automatically adjust the working state of the UAV according to the environmental status, and warn of potential faults in advance, thereby effectively improving the UAV's autonomous perception ability, fault warning and safe flight guarantee capabilities.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent fault alarm system in UAV environment perception, the system comprising the following components: an environment perception module, an environment parameter analysis and decision unit, a fault warning and alarm module and an adaptive adjustment module;

[0007] The environment sensing module integrates temperature sensors, pressure sensors and humidity sensors to collect temperature, air pressure and humidity parameters of the environment in which the drone is located in real time, pre-process the collected raw data, and store the processed data in the local storage of the drone or transmit it to a remote data center in real time;

[0008] The environmental parameter analysis and decision-making unit uses historical data and expert knowledge to establish a mapping relationship model between environmental parameters and UAV performance through an algorithm and conducts training. The real-time data collected by the environmental perception module is input into the established model for online analysis. The model will output the expected performance of the UAV in the current environment. According to the model prediction results, the environmental parameter analysis and decision-making unit will automatically generate a corresponding flight control strategy, and send the generated flight control strategy to the UAV's flight control system through the algorithm, and the flight control system will perform corresponding operations;

[0009] The fault warning and alarm module sets the warning thresholds of various environmental parameters and performance indicators according to the design parameters and performance requirements of the UAV during system initialization. During the flight of the UAV, the environmental parameters and the performance indicators of the UAV are continuously monitored, and the real-time monitored data are compared with the warning thresholds to determine whether there is an abnormal situation. Once an abnormal situation is detected, the corresponding alarm mechanism is immediately triggered. After the alarm is triggered, measures are taken according to the preset emergency handling process to ensure the safety of the UAV.

[0010] The adaptive adjustment module comprehensively evaluates the current environment of the UAV based on the output results of the environmental perception module and the environmental parameter analysis and decision-making unit, and automatically adjusts the flight parameters and system configuration of the UAV according to the environmental assessment results to adapt to the current environment. During the parameter adjustment process, the performance indicators of the UAV are continuously monitored, and the adjusted flight parameters and system configuration are compared and analyzed with the actual performance of the UAV, so as to continuously optimize the model and parameters of the environmental parameter analysis and decision-making unit;

[0011] The environmental parameter analysis and decision-making unit uses historical data and expert knowledge to establish a mapping relationship model between environmental parameters and UAV performance through an algorithm. The algorithm formula is: Among them, Q is the performance index of the drone, T is the ambient temperature, P is the ambient air pressure, H is the ambient humidity, and w i1 is the weight, a i , b i, c i are the coefficients of different input variables, θ1 is the bias, m is the number of input variables, and d is the constant term;

[0012] The environmental parameter analysis and decision-making unit sends the generated flight control strategy to the flight control system of the UAV through an algorithm, and the algorithm formula used is: Where: u(t) is the control command sent to the drone, e(t) is the difference between the current state and the desired state of the drone, K p , K i , K d They are proportional, integral, and differential gains, which are used to adjust the response speed and stability of the controller. is the integral of the error signal, used to eliminate steady-state errors, It is the differential of the error signal and is used to predict future error changes and improve the response speed of the system.

[0013] Furthermore, the specific steps of the environmental parameter analysis and decision-making unit for training the model are:

[0014] (1) Use the preprocessed data as a training set to train the model;

[0015] (2) During the training process, the model parameters are continuously adjusted to make the model better fit the training data;

[0016] (3) Use the test set to evaluate the trained model and calculate the model's accuracy, recall, and F1 score indicators;

[0017] (4) Apply the model to actual scenarios to verify its prediction accuracy under different environmental conditions.

[0018] Furthermore, the environmental parameter analysis and decision-making unit inputs the real-time data collected by the environmental perception module into the established model for online analysis. The model will output the expected performance of the UAV in the current environment, including: flight endurance, flight speed and stability, sensor and navigation accuracy, load capacity, wind resistance, and communication and data transmission capabilities.

[0019] Furthermore, the environmental parameter analysis and decision-making unit automatically generates corresponding flight control strategies based on the model prediction results. The specific strategies include: automatically adjusting the working mode of the cooling system in a high temperature environment, starting the battery insulation mechanism in a low temperature environment, and adjusting the flight attitude and power distribution in a high altitude environment.

[0020] Furthermore, once the fault warning and alarm module detects an abnormal situation, it immediately triggers a corresponding alarm mechanism, and the alarm mechanism includes: sounding an alarm, lighting a fault indicator light, and sending an alarm message to a remote operator.

[0021] Furthermore, when the system is initialized, the fault warning and alarm module sets warning thresholds for various environmental parameters and performance indicators according to the design parameters and performance requirements of the drone. The environmental thresholds include: setting high and low temperature warning thresholds according to the heat dissipation capacity of the drone and the temperature resistance range of the electronic components; for high-altitude flight, setting the air pressure warning threshold according to the drone's ceiling and the accuracy of the air pressure sensor; the performance indicator thresholds include: setting the warning thresholds for battery voltage and current according to the battery's performance curve and safe use range; setting the warning threshold for vibration level according to the vibration resistance of mechanical components and fault history data; and setting the warning threshold for attitude stability according to the attitude control accuracy and stability requirements of the drone.

[0022] Furthermore, after the alarm is triggered, the fault warning and alarm module takes measures to ensure the safety of the drone according to the preset emergency handling process, and the specific measures include:

[0023] (1) Automatically adjust the flight parameters of the UAV according to the fault type and severity, including lowering the flight altitude, slowing down the flight, and changing the flight attitude;

[0024] (2) Before a failure occurs, the system will regularly back up important data and parameter settings;

[0025] (3) In an emergency, the operator manually intervenes in the flight control of the UAV according to the alarm information and emergency operation instructions issued by the system;

[0026] (4) Record fault warning, emergency handling process and results in the UAV’s log system.

[0027] Furthermore, the adaptive adjustment module compares and analyzes the adjusted flight parameters and system configuration with the actual performance of the UAV, and continuously optimizes the model and parameters of the environmental parameter analysis and decision-making unit. The algorithm formula for the optimization is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results. This formula calculates the gradient of the loss function based on the current data and adjusts the model parameters based on the feedback.

[0028] Compared with the existing technology, the intelligent fault alarm system in the UAV environment perception has the following beneficial effects:

[0029] 1. The present invention integrates multiple sensors to monitor key parameters in extreme environments in real time, and combines intelligent algorithms for rapid analysis and decision-making, so as to timely discover and warn of potential risks that drones may face. In high-temperature environments, the automatically activated enhanced heat dissipation mode and high-temperature alarm effectively prevent overheating and damage of electronic components; in low-temperature environments, insulation measures for key components and low-temperature alarms ensure the stable performance of key components such as batteries, and avoid flight accidents caused by battery failure.

[0030] 2. Through the adaptive adjustment mechanism, the UAV of the present invention can automatically adjust the flight altitude, speed, power distribution and other parameters according to the real-time environmental parameters to ensure the best working state in different extreme environments. This intelligent adjustment not only reduces energy consumption, but also improves flight stability, allowing the UAV to operate efficiently in a wider range of environmental conditions.

[0031] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 Schematic diagram of the intelligent fault warning system in UAV environment perception. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Embodiment 1

[0036] This embodiment describes in detail the specific application process of the intelligent fault alarm system in drone environmental perception in a high-altitude environment.

[0037] In the hardware design of the UAV, high-strength lightweight materials are used to enhance the structural strength and wind resistance. It is also equipped with a redundant power supply system, dual flight control systems and multiple communication modules to ensure that the UAV can continue to perform its mission or return safely when some components fail. To cope with the low oxygen environment in high altitude areas, the UAV is specially equipped with an oxygen enrichment system and an efficient oxygen sensor to monitor the oxygen concentration in the cabin in real time to ensure the normal operation of key electronic components.

[0038] The environmental perception module not only integrates conventional temperature sensors, pressure sensors, and humidity sensors, but also adds wind speed and direction sensors, ultraviolet radiation sensors, etc. to obtain more comprehensive environmental information. It uses advanced data fusion technology to comprehensively process data from different sensors to improve the accuracy and reliability of environmental parameter measurements, and filters out noise and interference through algorithms to ensure the validity and real-time nature of the data.

[0039] The environmental parameter analysis and decision-making unit uses algorithms to continuously learn from historical flight data and real-time environmental data to optimize the mapping relationship model. The model algorithm formula is: Among them, Q is the performance index of the drone, T is the ambient temperature, P is the ambient air pressure, H is the ambient humidity, and w i1 is the weight, a i , b i , c i is the coefficient of different input variables, θ1 is the bias, m is the number of input variables, and d is the constant term model. The algorithm not only considers the impact of a single environmental parameter on the performance of the UAV, but also comprehensively evaluates the interaction between multiple factors to improve the accuracy of the prediction. The real-time data collected by the environmental perception module is input into the established model for online analysis. The model will output the expected performance of the UAV in the current environment. According to the model prediction results, the environmental parameter analysis and decision-making unit will automatically generate the corresponding flight control strategy, and send the generated flight control strategy to the UAV's flight control system through the algorithm. The flight control system performs the corresponding operations. At the same time, an adaptive learning mechanism is introduced to enable the model to automatically adjust parameters and weights according to the actual flight performance of the UAV. The algorithm formula for its optimization is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ histIt is the model parameter adjustment amount calculated based on the feedback results. This formula calculates the gradient of the loss function based on the current data, and adjusts the model parameters based on the feedback to continuously optimize the prediction results and flight control strategies.

[0040] The fault warning and alarm module has a multi-level alarm mechanism, which is divided into different levels of alarms according to the severity of the abnormal situation, such as yellow warning, orange alarm and red emergency status. Each alarm corresponds to different emergency handling processes and response measures. When a serious fault or emergency is detected, the UAV can automatically start the emergency landing procedure, find the nearest safe landing point and land. At the same time, through satellite communication and emergency positioning beacons, it sends accurate location information and distress signals to the ground control center. It is also equipped with advanced ground control stations and remote monitoring platforms, supporting real-time data transmission, video return and remote control functions of UAVs. Operators can monitor the flight status, environmental parameters and performance indicators of the UAV in real time through the ground control station, and conduct remote intervention and command as needed. Natural language processing and speech recognition technology are introduced to realize intelligent interaction between man and machine. Operators can quickly adjust flight parameters, query data or start specific functions through voice commands or natural language input.

[0041] During the flight, the drone can autonomously avoid obstacles and use laser radar, infrared sensors and other equipment to detect and avoid obstacles to ensure flight safety. After completing the mission, the drone automatically performs flight data analysis and performance evaluation. Based on the evaluation results, it generates maintenance reports and suggestions to guide subsequent maintenance and care work. It also regularly updates the drone's software and hardware, introduces the latest technologies and algorithms, and continuously improves the drone's performance and application capabilities.

[0042] To sum up, the intelligent UAV fault warning and adaptive flight system for extreme environments provided in this embodiment has demonstrated excellent environmental perception, intelligent decision-making, fault warning and adaptive adjustment capabilities in complex and changeable extreme environments, effectively improving the operating efficiency and safety of UAVs in extreme environments.

[0043] Embodiment 2

[0044] Based on the first embodiment, this embodiment describes in detail the specific application steps of the fault warning and alarm module in the intelligent fault alarm system in the drone environment perception.

[0045] When the fault warning and alarm module is initialized, the warning thresholds of various environmental parameters and performance indicators are set according to the design parameters and performance requirements of the UAV. The environmental thresholds include: setting high and low temperature warning thresholds according to the heat dissipation capacity of the UAV and the temperature resistance range of the electronic components; for high-altitude flight, setting the air pressure warning threshold according to the UAV's ceiling and the accuracy of the air pressure sensor; the performance indicator thresholds include: setting the warning thresholds of battery voltage and current according to the battery's performance curve and safe use range; setting the warning threshold of vibration level according to the vibration resistance of mechanical components and fault history data; and setting the warning threshold of attitude stability according to the attitude control accuracy and stability requirements of the UAV.

[0046] During the flight of the drone, the environmental parameters and the performance indicators of the drone are continuously monitored, and the real-time monitored data is compared with the warning threshold to determine whether there are any abnormal conditions. Once an abnormal condition is detected, the corresponding alarm mechanism is immediately triggered. The alarm mechanism includes: sounding an alarm, lighting up the fault indicator light and sending an alarm message to the remote operator.

[0047] After the alarm is triggered, measures are taken to ensure the safety of the drone according to the preset emergency response process. The specific measures include:

[0048] (1) Automatically adjust the flight parameters of the UAV according to the fault type and severity, including lowering the flight altitude, slowing down the flight, and changing the flight attitude;

[0049] (2) Before a failure occurs, the system will regularly back up important data and parameter settings;

[0050] (3) In an emergency, the operator manually intervenes in the flight control of the UAV according to the alarm information and emergency operation instructions issued by the system;

[0051] (4) Record fault warning, emergency handling process and results in the UAV’s log system.

[0052] In summary, the fault warning and alarm system of the present invention demonstrates its powerful real-time monitoring, intelligent warning and remote communication capabilities, effectively improving the safety and mission completion rate of drones in extreme environments.

[0053] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. Intelligent fault alarm system in drone environment perception, characterized by: The system includes the following components: environmental perception module, environmental parameter analysis and decision-making unit, fault warning and alarm module and adaptive adjustment module; The environmental perception module integrates temperature sensors, pressure sensors and humidity sensors to collect temperature, air pressure and humidity parameters of the environment where the drone is located in real time, pre-process the collected raw data, and process the processed data; The environmental parameter analysis and decision-making unit uses historical data and expert knowledge to establish a mapping relationship model between environmental parameters and UAV performance through an algorithm and conducts training. The real-time data collected by the environmental perception module is input into the established model for online analysis. The model will output the expected performance of the UAV in the current environment. According to the model prediction results, the environmental parameter analysis and decision-making unit will automatically generate a corresponding flight control strategy, and send the generated flight control strategy to the flight control system of the UAV through the algorithm. The fault warning and alarm module sets the warning thresholds of various environmental parameters and performance indicators according to the design parameters and performance requirements of the UAV during system initialization. By continuously monitoring the environmental parameters and the performance indicators of the UAV, the real-time monitored data is compared with the warning thresholds to determine whether there is an abnormal situation. Once an abnormal situation is detected, the corresponding alarm mechanism is immediately triggered. After the alarm is triggered, measures are taken according to the preset emergency handling process to ensure the safety of the UAV. The adaptive adjustment module comprehensively evaluates the current environment of the UAV based on the output results of the environmental perception module and the environmental parameter analysis and decision-making unit, and automatically adjusts the flight parameters and system configuration of the UAV according to the environmental assessment results to adapt to the current environment. During the parameter adjustment process, the performance indicators of the UAV are continuously monitored, and the adjusted flight parameters and system configuration are compared and analyzed with the actual performance of the UAV, so as to continuously optimize the model and parameters of the environmental parameter analysis and decision-making unit.

2. The intelligent fault alarm system in drone environment perception according to claim 1 is characterized in that: The environmental parameter analysis and decision-making unit uses historical data and expert knowledge to establish a mapping relationship model between environmental parameters and UAV performance through an algorithm, and its algorithm formula is: Q = f Among them, Q is the performance index of the drone, T is the ambient temperature, P is the ambient air pressure, H is the ambient humidity, and w i1 is the weight, a i , b i , c i are the coefficients for the different input variables, θ1 is the bias, m is the number of input variables, and d is the constant term.

3. The intelligent fault alarm system in drone environment perception according to claim 1 is characterized in that: The specific steps of the environmental parameter analysis and decision-making unit to train the model are: (1) Use the preprocessed data as a training set to train the model; (2) During the training process, the model parameters are continuously adjusted to make the model better fit the training data; (3) Use the test set to evaluate the trained model and calculate the model's accuracy, recall, and F1 score indicators; (4) Apply the model to actual scenarios to verify its prediction accuracy under different environmental conditions.

4. The intelligent fault alarm system in drone environment perception according to claim 1 is characterized in that: The environmental parameter analysis and decision-making unit inputs the real-time data collected by the environmental perception module into the established model for online analysis. The model will output the expected performance of the UAV in the current environment, including: flight endurance, flight speed and stability, sensor and navigation accuracy, load capacity, wind resistance, and communication and data transmission capabilities.

5. The intelligent fault alarm system in drone environment perception according to claim 1 is characterized in that: The environmental parameter analysis and decision-making unit automatically generates corresponding flight control strategies based on the model prediction results. The specific strategies include: automatically adjusting the working mode of the cooling system in a high-temperature environment, starting the battery insulation mechanism in a low-temperature environment, and adjusting the flight attitude and power distribution in a high-altitude environment.

6. The intelligent fault alarm system in drone environment perception according to claim 5 is characterized in that: The environmental parameter analysis and decision-making unit sends the generated flight control strategy to the flight control system of the UAV through an algorithm, and the algorithm formula used is: Where: u(t) is the control command sent to the drone, e(t) is the difference between the current state and the desired state of the drone, K p , K i , K d They are proportional, integral, and differential gains, which are used to adjust the response speed and stability of the controller. is the integral of the error signal, used to eliminate steady-state errors, It is the differential of the error signal and is used to predict future error changes and improve the response speed of the system.

7. The intelligent fault alarm system in drone environment perception according to claim 1 is characterized in that: Once the fault warning and alarm module detects an abnormal situation, it immediately triggers a corresponding alarm mechanism, which includes: sounding an alarm, lighting a fault indicator light, and sending an alarm message to a remote operator.

8. The intelligent fault alarm system in drone environment perception according to claim 1 is characterized in that: The fault warning and alarm module sets warning thresholds of various environmental parameters and performance indicators according to the design parameters and performance requirements of the UAV during system initialization. The environmental thresholds include: setting high temperature and low temperature warning thresholds according to the heat dissipation capacity of the UAV and the temperature resistance range of the electronic components; for high-altitude flight, setting the air pressure warning threshold according to the UAV's ceiling and the accuracy of the air pressure sensor; the performance indicator thresholds include: setting the warning thresholds of battery voltage and current according to the battery's performance curve and safe use range; setting the warning threshold of vibration level according to the vibration resistance of mechanical parts and fault history data; and setting the warning threshold of attitude stability according to the attitude control accuracy and stability requirements of the UAV.

9. The intelligent fault alarm system in drone environment perception according to claim 1, characterized in that: After the alarm is triggered, the fault warning and alarm module takes measures to ensure the safety of the drone according to the preset emergency handling process. The specific measures include: (1) Automatically adjust the flight parameters of the UAV according to the fault type and severity, including lowering the flight altitude, slowing down the flight, and changing the flight attitude; (2) Before a failure occurs, the system will regularly back up important data and parameter settings; (3) In an emergency, the operator manually intervenes in the flight control of the UAV according to the alarm information and emergency operation instructions issued by the system; (4) Record fault warning, emergency handling process and results in the UAV’s log system.

10. The intelligent fault alarm system in drone environment perception according to claim 1, characterized in that: The adaptive adjustment module compares and analyzes the adjusted flight parameters and system configuration with the actual performance of the UAV, and continuously optimizes the model and parameters of the environmental parameter analysis and decision-making unit. The algorithm formula for the optimization is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results. This formula calculates the gradient of the loss function based on the current data and adjusts the model parameters based on the feedback.

Images